wechat-article-writer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly fetches and ingests arbitrary website content and web search results (e.g., "输入识别: 网站链接：使用 web_fetch 获取完整内容" and the use of exa:web_search_exa in the core workflow and examples), so it consumes untrusted public web content that the agent must read and use to drive research and article-writing decisions.